{"version":"2.1.235","anchor":"untrusted-text-in-permission-and-elicitation-dialogs-is-trun","canonical_anchor":"untrusted-text-in-permission-and-elicitation-dialogs-is-trun","heading":"Untrusted text in permission and elicitation dialogs is truncated and sanitized","tier":"notice","area":"Permissions","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.235\/e\/untrusted-text-in-permission-and-elicitation-dialogs-is-trun","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.235","markdown":"### Untrusted text in permission and elicitation dialogs is truncated and sanitized\n\nUntrusted text shown in permission and elicitation dialogs is now sanitized and length-capped\n\nText drawn from MCP elicitation requests, WebSocket\/MCP tool descriptors, Bash commands, skill names and descriptions, notebook cell ids, and select-artifact labels now passes through display sanitizers with a size cap before being rendered, instead of being shown raw; MCP server and tool names fall back to placeholders like \"(unnamed server)\" when needed. In the elicitation URL dialog, the accept option is only pre-selected when both the message and URL round-trip cleanly with no newlines, and the accept handler refuses to open the URL otherwise. Option previews that are too long are marked withheld and their always-allow rows are suppressed.\n\n- Area: Permissions\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5"}